Autoencoders for semivisible jet detection

Abstract

The production of dark matter particles from confining dark sectors may lead to many novel experimental signatures. Depending on the details of the theory, dark quark production in proton-proton collisions could result in semivisible jets of particles: collimated sprays of dark hadrons of which only some are detectable by particle collider experiments. The experimental signature is characterised by the presence of reconstructed missing momentum collinear with the visible components of the jets. This complex topology is sensitive to detector inefficiencies and mis-reconstruction that generate artificial missing momentum. With this work, we propose a signal-agnostic strategy to reject ordinary jets and identify semivisible jets via anomaly detection techniques. A deep neural autoencoder network with jet substructure variables as input proves highly useful for analyzing anomalous jets. The study focuses on the semivisible jet signature; however, the technique can apply to any new physics model that predicts signatures with anomalous jets from non-SM particles.

Theory, phenomenology, and experimental avenues for dark showers: a Snowmass 2021 report

“…Searches for dark showers exploit jet substructure (JSS) observables to tag jets as dark jets [86,183]. Comparisons of jet substructure variables of interest, between the former and the new Hidden Valley pythia modules, and between different dark vector meson production probabilities, are presented in this section.…”

“…Refs. [195,67,196,197,198,68,69,183]) and exploiting the special relation between the azimuthal direction of the semivisible jets and the missing transverse momentum p T miss (see e.g. Refs.…”

“…cosmological measurements. Since it is impractical to perform dedicated searches for all possible model variations, we propose to use autoencoders (AE) as anomalous jets taggers instead [183].…”

IRC-Safe Graph Autoencoder for Unsupervised Anomaly Detection

“…This anomaly detection has emerged as a powerful tool to look for any hidden signature of new physics in the data. Recently, a range of state-of-the-art methods for anomaly detection (Collins et al, 2018(Collins et al, , 2021Aaboud et al, 2019;Blance et al, 2019;De Simone and Jacques, 2019;Blance and Spannowsky, 2020;Cheng et al, 2020;Hajer et al, 2020;Nachman, 2020;Nachman and Shih, 2020;Araz and Spannowsky, 2021;Atkinson et al, 2021b;Hallin et al, 2021;Canelli et al, 2022) using deep learning have been designed.…”

IRC-safe Graph Autoencoder for an unsupervised anomaly detection

“…This anomaly detection has emerged as a powerful tool to look for any hidden signature of new physics in the data. Recently, a range of state-of-the-art methods for anomaly detection [5][6][7][8][9][10][11][12][13][14][15][16][17][18] using deep learning have been designed.…”